© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16936
    Prev
    Next
    INDEX
    Explanations

    references to being observed or noticed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dera
    -0.06
    ahas
    -0.06
    isz
    -0.06
    chop
    -0.06
    /cs
    -0.06
    ÏĦοκ
    -0.06
     Chow
    -0.06
    elves
    -0.06
    pering
    -0.06
    éis
    -0.06
    POSITIVE LOGITS
     carrying
    0.07
    ritel
    0.07
    ãģ¹
    0.07
    rlen
    0.06
     Horton
    0.06
    .beh
    0.06
    liÄį
    0.06
    ìĨ¡
    0.06
    312
    0.06
     DISCLAIMER
    0.06
    Activations Density 0.009%

    No Known Activations